（1）D2系：半监督目标检测训练自己的数据集unbiased-teacher

半监督目标检测复现

`相关：最近再做半监督目标检测的课题，记录一下当前一些算法的复现，目前仅复现了D2系的unbiased-teacher 和改进版mix-unmix算法，mmcv系的soft teacher ，pseco和Instant-teacher。后续复现成功后会有补充。文中的方式是基于ubuntu 系统的conda安装的COCO数据集格式。

---

---

D2系： 1-unbiased-teacher

1、根据readme创建基础环境
#create conda env
这里原文使用的python为3.6，但由于第二步中d2需要python 3.7以上的版本，所以这里更改为3.7
conda create -n detectron2 python=3.7
#activate the enviorment
conda activate detectron2
#install PyTorch >=1.5 with GPU，这里要和d2所需环境保持一致，所以需要pytorch1.8以上的版本，具体安装指令参考pytorch官网。pytorch历代版本官网
conda install pytorch torchvision -c pytorch
2、根据detectron2安装d2
这里就按照官网进行安装即可
方法1：python -m pip install ‘git+https://github.com/facebookresearch/detectron2.git’
#（add --user if you don’t have permission)

#Or, to install it from a local clone:
方法2：git clone https://github.com/facebookresearch/detectron2.git
python -m pip install -e detectron2

#On macOS, you may need to prepend the above commands with a few environment variables:
方法3：CC=clang CXX=clang++ ARCHFLAGS=“-arch x86_64” python -m pip install …

3、安装好上述环境之后，copy一下原文的代码：
https://github.com/facebookresearch/unbiased-teacher

4、训练自己的数据集：
本文的方式是将数据集信息直接添加到代码中的train_net.py
第一步：更改train_net.py

#!/usr/bin/env python3
#Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
import os
import detectron2.utils.comm as comm
from detectron2.checkpoint import DetectionCheckpointer
from detectron2.config import get_cfg
from detectron2.engine import default_argument_parser, default_setup, launch

from ubteacher import add_ubteacher_config
from ubteacher.engine.trainer import UBTeacherTrainer, BaselineTrainer

#hacky way to register
from ubteacher.modeling.meta_arch.rcnn import TwoStagePseudoLabGeneralizedRCNN
from ubteacher.modeling.proposal_generator.rpn import PseudoLabRPN
from ubteacher.modeling.roi_heads.roi_heads import StandardROIHeadsPseudoLab
import ubteacher.data.datasets.builtin

##############################################
从这里开始添加注册数据集信息
#############################################
from ubteacher.modeling.meta_arch.ts_ensemble import EnsembleTSModel

from detectron2.data import DatasetCatalog, MetadataCatalog
from detectron2.data.datasets.coco import load_coco_json
import pycocotools
#声明类别，尽量保持
CLASS_NAMES =["类别"]
#数据集路径
DATASET_ROOT = ''
ANN_ROOT = os.path.join(DATASET_ROOT, 'annotations/')

#图像路径
TRAIN_PATH = os.path.join(DATASET_ROOT, 'images')
VAL_PATH = os.path.join(DATASET_ROOT, 'images')
#coco数据集的json标注路径
TRAIN_LABEL_JSON =  os.path.join(ANN_ROOT, 'instances_train2014.json')
TRAIN_UNLABEL_JSON = os.path.join(ANN_ROOT, 'instances_train2014_unlabel.json')
#VAL_JSON = os.path.join(ANN_ROOT, 'val.json')
VAL_JSON = os.path.join(ANN_ROOT, 'instances_val2014.json')

#声明数据集的子集
PREDEFINED_SPLITS_DATASET = {
    "coco_train_label": (TRAIN_PATH, TRAIN_LABEL_JSON),
    "coco_train_unlabel": (TRAIN_PATH, TRAIN_UNLABEL_JSON),
    "coco_val": (VAL_PATH, VAL_JSON),
}

#=============================
#注册数据集和元数据
def plain_register_dataset():
    #训练集
    DatasetCatalog.register("coco_train_label", lambda: load_coco_json(TRAIN_LABEL_JSON, TRAIN_PATH))
    MetadataCatalog.get("coco_train_label").set(thing_classes=CLASS_NAMES,  # 可以选择开启，但是不能显示中文，这里需要注意，中文的话最好关闭
                                                    evaluator_type='coco', # 指定评估方式
                                                    json_file=TRAIN_LABEL_JSON,
                                                    image_root=TRAIN_PATH)
    DatasetCatalog.register("coco_train_unlabel", lambda: load_coco_json(TRAIN_UNLABEL_JSON, TRAIN_PATH))
    MetadataCatalog.get("coco_train_unlabel").set(thing_classes=CLASS_NAMES,  # 可以选择开启，但是不能显示中文，这里需要注意，中文的话最好关闭
                                                    evaluator_type='coco', # 指定评估方式
                                                    json_file=TRAIN_UNLABEL_JSON,
                                                    image_root=TRAIN_PATH)                                                

    #DatasetCatalog.register("coco_my_val", lambda: load_coco_json(VAL_JSON, VAL_PATH, "coco_2017_val"))
    #验证/测试集
    DatasetCatalog.register("coco_val", lambda: load_coco_json(VAL_JSON, VAL_PATH))
    MetadataCatalog.get("coco_val").set(thing_classes=CLASS_NAMES, # 可以选择开启，但是不能显示中文，这里需要注意，中文的话最好关闭
                                                evaluator_type='coco', # 指定评估方式
                                                json_file=VAL_JSON,
                                                image_root=VAL_PATH)

###############################################
def setup(args):
    """
    Create configs and perform basic setups.
    """
    cfg = get_cfg()
    add_ubteacher_config(cfg)
    cfg.merge_from_file(args.config_file)
    cfg.merge_from_list(args.opts)
    cfg.freeze()
    default_setup(cfg, args)
    return cfg


def main(args):
    cfg = setup(args)
    #新增运行数据集的注册
    plain_register_dataset()
    
    if cfg.SEMISUPNET.Trainer == "ubteacher":
        Trainer = UBTeacherTrainer
    elif cfg.SEMISUPNET.Trainer == "baseline":
        Trainer = BaselineTrainer
    else:
        raise ValueError("Trainer Name is not found.")

    if args.eval_only:
        if cfg.SEMISUPNET.Trainer == "ubteacher":
            model = Trainer.build_model(cfg)
            model_teacher = Trainer.build_model(cfg)
            ensem_ts_model = EnsembleTSModel(model_teacher, model)

            DetectionCheckpointer(
                ensem_ts_model, save_dir=cfg.OUTPUT_DIR
            ).resume_or_load(cfg.MODEL.WEIGHTS, resume=args.resume)
            res = Trainer.test(cfg, ensem_ts_model.modelTeacher)

        else:
            model = Trainer.build_model(cfg)
            DetectionCheckpointer(model, save_dir=cfg.OUTPUT_DIR).resume_or_load(
                cfg.MODEL.WEIGHTS, resume=args.resume
            )
            res = Trainer.test(cfg, model)
        return res

    trainer = Trainer(cfg)
    trainer.resume_or_load(resume=args.resume)

    return trainer.train()


if __name__ == "__main__":
    args = default_argument_parser().parse_args()

    print("Command Line Args:", args)
    launch(
        main,
        args.num_gpus,
        num_machines=args.num_machines,
        machine_rank=args.machine_rank,
        dist_url=args.dist_url,
        args=(args,),
    )

第二步，修改/mnt/sdd/zhanghexiang/unbiased-teacher/configs/coco_supervision/faster_rcnn_R_50_FPN_sup10_run1.yaml配置文件，将训练数据集的来源由原来的

替换为：

注意：这里的名字要和train_net.py里面注册的名字保持一致。然后就可以按照readme里面的指令进行训练了。我的话用的是2张卡，所以是：
根据卡的大小调一下batch就行。

CUDA_VISIBLE_DEVICES=3,4 nohup python train_net.py       --num-gpus 2       --config configs/coco_supervision/faster_rcnn_R_50_FPN_sup10_run1.yaml        SOLVER.IMG_PER_BATCH_LABEL 4 SOLVER.IMG_PER_BATCH_UNLABEL 4